Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/cwinvestments/memstack/facebook-adnpx skills add cwinvestments/memstack --skill facebook-adgit clone --depth 1 https://github.com/cwinvestments/memstackWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00064 | $0.02757 |
| Opus 5 | $0.00032 | $0.01378 |
| Sonnet 5 | $0.00013 | $0.00551 |
| Haiku 4.5 | $0.00006 | $0.00276 |
Grade A, and why
memstack-marketing-facebook-ad scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 320 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Facebook Ad — Creating Meta ad campaign...
Creates complete ad campaigns with audience targeting, ad copy variations, creative direction, budget allocation, and A/B testing protocol for Meta Ads Manager.
Activation
When this skill activates, output:
Facebook Ad — Creating Meta ad campaign...
Then execute the protocol below.
Context Guard
| Context | Status |
|---|---|
| User says "Facebook ad", "FB ad", "Meta ad", "Instagram ad" | ACTIVE |
| User needs social media ad copy with targeting | ACTIVE |
| User wants to run paid campaigns on Meta platforms | ACTIVE |
| User wants Google Search or Display ads | DORMANT — use Google Ad |
| User wants organic social media content | DORMANT — not an ad skill |
Common Mistakes
| Mistake | Why It's Wrong |
|---|---|
| "Target everyone" | Broad audiences burn budget. Start narrow (1-5M), expand after finding winners. |
| "One ad, one audience" | Always test 3-5 ad variations per ad set. Meta's algorithm needs options. |
| "Start with $5/day" | Too little for the algorithm to learn. Minimum $20/day per ad set for meaningful data. |
| "Judge ads after 24 hours" | Meta needs 50+ conversions per ad set per week to exit learning phase. Wait 3-7 days. |
| "Use stock photos" | UGC-style creative outperforms polished studio content 2-3x on Meta. |
Protocol
Step 1: Gather Campaign Requirements
If the user hasn't provided details, ask:
- Product/service — what are you promoting? (name, price, URL)
- Objective — leads, sales, traffic, or brand awareness?
- Target audience — who is the ideal customer? (age, interests, pain points)
- Budget — daily or monthly ad spend?
- Existing assets — do you have customer testimonials, product photos, or video?
- Previous campaigns — any past Meta ads data to build on?
Step 2: Define Campaign Structure
Build the campaign using Meta's three-tier hierarchy:
Campaign (1 objective)
├── Ad Set 1: [Audience A] — $[budget]/day
│ ├── Ad 1: [Hook A + Creative A]
│ ├── Ad 2: [Hook B + Creative A]
│ └── Ad 3: [Hook A + Creative B]
├── Ad Set 2: [Audience B] — $[budget]/day
│ ├── Ad 1: [Hook A + Creative A]
│ ├── Ad 2: [Hook B + Creative A]
│ └── Ad 3: [Hook A + Creative B]
└── Ad Set 3: [Lookalike/Retargeting] — $[budget]/day
├── Ad 1: [Social proof hook]
├── Ad 2: [Urgency hook]
└── Ad 3: [Testimonial creative]
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 3d ago First seen · 320 lines · 64 tokens per session scan A aa72e720923f
memstack-marketing-facebook-ad is a skill published in the GitHub repository cwinvestments/memstack (419 stars, last pushed 6d ago), licensed MIT. It adds 64 tokens to every session and 2,757 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
rulesync
Generates and syncs AI rule configuration files (.cursorrules, CLAUDE.md, copilot-instructions.md) across 20+ coding tools from a single source. Use when syncing AI rules, running rulesync commands, importing or generating rule files, or managing shared AI coding configurations.
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.
autoprompt
Explicit-only useful-first orchestration. Invoke /autoprompt to turn a mission into one executable roadmap, build dependency-safe lanes, and verify the result with independent reviewers. Never infer invocation from ordinary requests. Never resume from leftover artifacts without an explicit resume instruction.
office-hours
YC Office Hours — two modes. Startup mode: six forcing questions that expose demand reality, status quo, desperate specificity, narrowest wedge, observation, and future-fit. Builder mode: design thinking brainstorming for side projects, hackathons, learning, and open source. Saves a design doc. Use when asked to…
backend-builder
Используй только внутри активного Codex Project Autopilot-проекта по утверждённому плану; не включай для обычных backend-задач вне автопилота.
loongsuite-pilot-insight
基于 LoongSuite Pilot / AI Coding Agent 日志生成事件洞察、组织洞察、数据质量、研发效能和 AI Native 使用类 SLS 报表时使用；包含 AI Coding 事件表语义，以及团队报表可选的部门维表、deptuser 组织关系、指标口径和公共 CTE，通常与 sls-dashboard-builder 一起使用。.